New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
BFCL v4 benchmark
AI model leaderboard for the BFCL v4 benchmark. Compare how large language models score on BFCL v4, see the full ranking, and understand what this AI benchmark measures. Berkeley Function-Calling Leaderboard, version 4.
Leaderboard
No model scores reported yet.
Frequently asked questions about BFCL v4
What is the BFCL v4 benchmark?
Berkeley Function-Calling Leaderboard, version 4.
How is the BFCL v4 benchmark scored?
BFCL v4 is scored using the accuracy (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on BFCL v4?
No model scores have been reported for BFCL v4 yet. Check back as the leaderboard is updated.
Is a higher BFCL v4 score better?
Yes. On BFCL v4 a higher score indicates better performance, so models near the top of the leaderboard are the strongest.